Published February 9, 2023 | Version v1

Dataset of Manufacturing Tasks - DMT22

  • 1. Universidade de Coimbra

Description

Description: The dataset of manufacturing tasks (DMT22), features five representative assembly primitive actions (PickUp, Place, Screw, Idle and Hold), collected from 5 different subjects featuring 3 different objects, a Wii remote, a hard disk drive, and an electric screwdriver.

Available Data: The DMT22 dataset contains recorded data from an event camera (DAVIS 240C), a depth camera (Intel RealSense D435) and a magnetic tracking system (Polhemus Liberty).

  • The event camera captured events and APS frames with a resolution of 240 pixels × 180 pixels. DAVIS APS data are captured at 30 fps (frames per second). Event data is available in the original recorded format, .aedat, together with a .txt file containing label and its corresponding timestamp range, and a .mat file which contains the information from the events (coordinates x and y, timestamp and polarity).
  • The electromagnetic tracker was used to capture pose data, at 20 Hz, from a sensor attached to the subject’s
    wrist. The data is available in .mat format. It contains 6DOF data (position and orientation) followed by the timestamp of measured data (relative to the start of the recording).
  • RGB-D camera data is available, at 30fps, in the original recorded format, .bag.

The dataset features a total of 72 recordings: 4 right-handed subjects × 3 tasks × 4 performances + 1 left-handed subject × 2 configurations (left and right) × 3 tasks × 4 performances. Each task recording lasts approximately 25 seconds.

 

Files

Files (26.0 GB)

Name Size
md5:173f5524894b9282116c496ee5859959
563.5 MB Download
md5:93b74baf88ea6b4fae8d446619c2bf81
659.7 MB Download
md5:837b8fac5c3979fbad698268618f0c2d
734.9 MB Download
md5:d20a3b5a2ef68e682928276ec9fa7809
698.6 MB Download
md5:d74703d9a511f629526267b6338c3d7d
566.4 MB Download
md5:6d7fc813315cb46d781abc74c3926049
645.1 MB Download
md5:fcff2ddeb31fdcd19a650fe0893c29ae
1.3 MB Download
md5:fc4dc7d93091164e50b9aee6745fa50f
3.2 GB Download
md5:82a840fbd8519a77aa3022a5d2650c79
3.8 GB Download
md5:59818a7e2d1dd12c01b56bb6bc2ec85a
4.5 GB Download
md5:6120c2b346c29fdd371c1a9a1e761e81
3.6 GB Download
md5:c8d6607c7541e7230f8a9f710ac4cf09
3.2 GB Download
md5:bcc0f6076a39243ea80b4522ad9f5bb7
3.6 GB Download

Additional details

Related works

Is described by
Journal article: 10.1016/j.jmsy.2023.03.001 (DOI)

Funding

Fundação para a Ciência e Tecnologia
Cognitive and safe robot interfaces through action anticipation for the classification of manufacturing primitives 2021.06508.BD